runtime error

<00:00, 43.0MB/s] Downloading model.safetensors: 100%|█████████▉| 377M/378M [00:15<00:00, 47.4MB/s] Downloading model.safetensors: 100%|██████████| 378M/378M [00:15<00:00, 24.9MB/s] Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base-960h and are newly initialized: ['wav2vec2.masked_spec_embed'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. Downloading (…)okenizer_config.json: 0%| | 0.00/163 [00:00<?, ?B/s] Downloading (…)okenizer_config.json: 100%|██████████| 163/163 [00:00<00:00, 1.20MB/s] Downloading (…)olve/main/vocab.json: 0%| | 0.00/291 [00:00<?, ?B/s] Downloading (…)olve/main/vocab.json: 100%|██████████| 291/291 [00:00<00:00, 2.29MB/s] Downloading (…)cial_tokens_map.json: 0%| | 0.00/85.0 [00:00<?, ?B/s] Downloading (…)cial_tokens_map.json: 100%|██████████| 85.0/85.0 [00:00<00:00, 658kB/s] Ignored unknown kwarg option normalize Ignored unknown kwarg option normalize Ignored unknown kwarg option normalize Ignored unknown kwarg option normalize Downloading (…)rocessor_config.json: 0%| | 0.00/159 [00:00<?, ?B/s] Downloading (…)rocessor_config.json: 100%|██████████| 159/159 [00:00<00:00, 1.54MB/s] Model selected: GPT-3.5 Setting model to GPT-3.5 Loading GPT-3.5 Traceback (most recent call last): File "/home/user/app/app.py", line 99, in <module> set_model(chatbot, radio.value) File "/home/user/app/app.py", line 57, in set_model index(model) File "/home/user/app/main.py", line 5, in index get_search_index(model) File "/home/user/app/utils.py", line 97, in get_search_index search_index = pickle.load(f) AttributeError: Can't get attribute '_default_relevance_score_fn' on <module 'langchain.vectorstores.faiss' from '/home/user/.local/lib/python3.10/site-packages/langchain/vectorstores/faiss.py'>

Container logs: